HIGHLIGHTS
- who: Seokjin Oh et al. from the School of Electrical Engineering, Kookmin University, Seoul, Republic of Korea have published the research work: Area-Efficient Mapping of Convolutional Neural Networks to Memristor Crossbars Using Sub-Image Partitioning, in the Journal: Micromachines 2023, 309 of 25/01/2023
- what: In this paper various convolution schemes with 3D 2D and 1D kernels are analyzed and compared in terms of neural network`s performance and overlapping overhead. Based on the analysis of Figure 2d, the authors discuss how to mitigate the line resistance problem in memristor crossbars in the . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.